update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the OPENSLR_SLR66 - NA dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
-
- Wer:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -45,11 +45,33 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 2000
|
| 48 |
-
- num_epochs:
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the OPENSLR_SLR66 - NA dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2719
|
| 20 |
+
- Wer: 0.3419
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 2000
|
| 48 |
+
- num_epochs: 100.0
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 3.0304 | 4.81 | 500 | 1.5676 | 1.0554 |
|
| 56 |
+
| 1.5263 | 9.61 | 1000 | 0.4693 | 0.8023 |
|
| 57 |
+
| 1.5299 | 14.42 | 1500 | 0.4368 | 0.7311 |
|
| 58 |
+
| 1.5063 | 19.23 | 2000 | 0.4360 | 0.7302 |
|
| 59 |
+
| 1.455 | 24.04 | 2500 | 0.4213 | 0.6692 |
|
| 60 |
+
| 1.4755 | 28.84 | 3000 | 0.4329 | 0.5943 |
|
| 61 |
+
| 1.352 | 33.65 | 3500 | 0.4074 | 0.5765 |
|
| 62 |
+
| 1.3122 | 38.46 | 4000 | 0.3866 | 0.5630 |
|
| 63 |
+
| 1.2799 | 43.27 | 4500 | 0.3860 | 0.5480 |
|
| 64 |
+
| 1.212 | 48.08 | 5000 | 0.3590 | 0.5317 |
|
| 65 |
+
| 1.1645 | 52.88 | 5500 | 0.3283 | 0.4757 |
|
| 66 |
+
| 1.0854 | 57.69 | 6000 | 0.3162 | 0.4687 |
|
| 67 |
+
| 1.0292 | 62.5 | 6500 | 0.3126 | 0.4416 |
|
| 68 |
+
| 0.9607 | 67.31 | 7000 | 0.2990 | 0.4066 |
|
| 69 |
+
| 0.9156 | 72.12 | 7500 | 0.2870 | 0.4009 |
|
| 70 |
+
| 0.8329 | 76.92 | 8000 | 0.2791 | 0.3909 |
|
| 71 |
+
| 0.7979 | 81.73 | 8500 | 0.2770 | 0.3670 |
|
| 72 |
+
| 0.7144 | 86.54 | 9000 | 0.2841 | 0.3661 |
|
| 73 |
+
| 0.6997 | 91.35 | 9500 | 0.2721 | 0.3485 |
|
| 74 |
+
| 0.6568 | 96.15 | 10000 | 0.2681 | 0.3437 |
|
| 75 |
|
| 76 |
|
| 77 |
### Framework versions
|